{"id":"https://openalex.org/W3137976833","doi":"https://doi.org/10.1109/icassp39728.2021.9413734","title":"Joint ASR and Language Identification Using RNN-T: An Efficient Approach to Dynamic Language Switching","display_name":"Joint ASR and Language Identification Using RNN-T: An Efficient Approach to Dynamic Language Switching","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3137976833","doi":"https://doi.org/10.1109/icassp39728.2021.9413734","mag":"3137976833"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091756317","display_name":"Surabhi Punjabi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surabhi Punjabi","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080360704","display_name":"Harish Arsikere","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Arsikere","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030676855","display_name":"Zeynab Raeesy","orcid":"https://orcid.org/0000-0002-7153-1963"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeynab Raeesy","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057924649","display_name":"Chander Chandak","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chander Chandak","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070412237","display_name":"Nikhil Bhave","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Bhave","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049198874","display_name":"Ankish Bansal","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankish Bansal","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106134095","display_name":"Markus M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Markus Muller","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113789062","display_name":"Sergio Murillo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergio Murillo","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110389578","display_name":"Sri Garimella","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sri Garimella","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090454997","display_name":"Roland Maas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roland Maas","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mat Hans","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mat Hans","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573067","display_name":"Athanasios Mouchtaris","orcid":"https://orcid.org/0000-0001-7583-0189"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Athanasios Mouchtaris","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074068808","display_name":"Siegfried Kunzmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siegfried Kunzmann","raw_affiliation_strings":["Alexa Machine Learning, Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa Machine Learning, Amazon","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":16,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.099,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89118863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7218","last_page":"7222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8885315656661987},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6089547276496887},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5913243293762207},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5673615336418152},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5503876805305481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5204265713691711},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.45771992206573486},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4492276906967163},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4353090524673462},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4339229166507721},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3399166464805603},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07763338088989258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885315656661987},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6089547276496887},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5913243293762207},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5673615336418152},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5503876805305481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5204265713691711},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45771992206573486},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4492276906967163},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4353090524673462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4339229166507721},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3399166464805603},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07763338088989258},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1501286448","https://openalex.org/W1816313093","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1970890968","https://openalex.org/W1994606281","https://openalex.org/W2016076298","https://openalex.org/W2025198378","https://openalex.org/W2033436836","https://openalex.org/W2091746061","https://openalex.org/W2127982613","https://openalex.org/W2153433699","https://openalex.org/W2786835190","https://openalex.org/W2787998955","https://openalex.org/W2891616026","https://openalex.org/W2935756939","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962893195","https://openalex.org/W2963649564","https://openalex.org/W2964002616","https://openalex.org/W2971840980","https://openalex.org/W2972619908","https://openalex.org/W2981945448","https://openalex.org/W3008434450","https://openalex.org/W3015194534","https://openalex.org/W4301239768","https://openalex.org/W6630162575","https://openalex.org/W6638575559","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6748645090","https://openalex.org/W6769255071"],"related_works":["https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Conventional":[0],"dynamic":[1],"language":[2,25,92,105],"switching":[3],"enables":[4],"seamless":[5],"multilingual":[6],"interactions":[7],"by":[8,143],"running":[9],"several":[10],"monolingual":[11,122],"ASR":[12,72,123],"systems":[13],"in":[14],"parallel":[15],"and":[16,37,73,76,115,129],"triggering":[17],"the":[18,52,87,103,117,139],"appropriate":[19],"downstream":[20],"components":[21],"using":[22,66,90],"a":[23,67],"standalone":[24],"identification":[26],"(LID)":[27],"service.":[28],"Since":[29],"this":[30],"solution":[31],"is":[32],"neither":[33],"scalable":[34],"nor":[35],"cost-":[36],"memory-efficient,":[38],"especially":[39],"for":[40,71],"on-device":[41],"applications,":[42],"we":[43],"propose":[44],"end-to-end,":[45],"streaming,":[46],"joint":[47,64,78,119],"ASR-LID":[48],"architectures":[49,111],"based":[50],"on":[51],"recurrent":[53],"neural":[54],"network":[55],"transducer":[56],"framework.":[57],"Two":[58],"key":[59],"formulations":[60],"are":[61],"explored:":[62],"(1)":[63],"training":[65,79],"unified":[68],"output":[69],"space":[70],"LID":[74,99,131],"vocabularies,":[75],"(2)":[77],"viewed":[80],"as":[81],"multi-task":[82,110],"optimization.":[83],"We":[84],"also":[85],"evaluate":[86],"benefit":[88],"of":[89],"auxiliary":[91],"information":[93],"obtained":[94],"on-the-fly":[95],"from":[96],"an":[97],"acoustic":[98,130],"classifier.":[100],"Experiments":[101],"with":[102],"English-Hindi":[104],"pair":[106],"show":[107],"that:":[108],"(a)":[109],"perform":[112],"better":[113],"overall,":[114],"(b)":[116],"best":[118],"architecture":[120],"surpasses":[121],"(6.4\u20139.2%":[124],"word":[125],"error":[126,133],"rate":[127,134],"reduction)":[128,135],"(53.9\u201356.1%":[132],"baselines":[136],"while":[137],"reducing":[138],"overall":[140],"memory":[141],"footprint":[142],"up":[144],"to":[145],"46%.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
